Google has given its Gemini AI assistant a significant new capability: the ability to generate functional, interactive simulations directly inside a conversation. Starting April 9, 2026, Gemini Pro users can ask the assistant to visualize complex concepts and receive live, adjustable models they can manipulate in real time, rather than static images or fixed diagrams. This represents a meaningful shift in how AI assistants communicate understanding .

What Exactly Can Gemini's New Simulation Feature Do?

The new capability allows Gemini to create working simulations for a broad range of topics. Users can explore how molecules rotate, run physics engines, or investigate how gravitational forces create stable orbital paths. The key difference from previous outputs is interactivity. Instead of viewing a single fixed illustration, users can adjust parameters using sliders and input fields and watch the simulation respond in real time .

A concrete example illustrates the distinction. When exploring how the moon orbits Earth, users are no longer limited to a static diagram. The simulation includes adjustable variables such as initial velocity and gravitational strength. Change either parameter, and the simulated orbit updates immediately to reflect the new values. This allows users to explore the relationship between variables and develop intuition about causal relationships that text alone cannot convey .

The feature works by having the Gemini model generate code, most likely JavaScript or a similar web-rendering language, which is then executed within the chat interface. The model constructs the visualization from scratch in response to the specific query, which is why arbitrary or niche topics can produce usable output. A prompt about fractal geometry, for instance, can yield a render of fractal patterns alongside adjustable parameters .

How to Activate Interactive Simulations in Gemini?

• Select the Pro Model: Access requires explicitly selecting the Pro model from the prompt bar at gemini.google.com before submitting a request.
• Use Visualization Language: Phrase your question with "show me" or "help me visualize" before describing the concept you want to explore.
• Describe Your Topic: The scope of what qualifies as a complex concept is deliberately broad, ranging from molecular rotation to physics simulations to orbital mechanics.

The feature is rolling out globally to all Gemini app users, without the geographic or subscription restrictions that initially limited earlier capability launches. This represents a departure from staged rollouts that previously restricted access to specific markets or subscription tiers .

Why Is This Built on Gemini 3's Generative UI Technology?

This capability builds on a trajectory that Google has been advancing through its Gemini 3 model since November 2025. When Google launched Gemini 3 on November 18, 2025, the announcement introduced generative UI, a technical approach where the model constructs interfaces dynamically in response to a query rather than selecting from a library of pre-built templates. The model writes code for visualizations, games, widgets, and simulations and executes that code as part of the response .

Google first deployed Gemini 3 in Search with model-designed interfaces on December 18, 2025, following the November 18 model launch. The April 9 update brings comparable output to the dedicated Gemini application, making it accessible to a much wider user base than the AI Mode in Google Search, where generative UI first appeared .

"I was teaching my daughter about lift and I asked it to create a simulation or a visualization for it and it made this crazy little window with vectors, like arrows running over a wing. Through these sliders, it would adjust the wing and then show how much lift was occurring, like, where the arrows would start under the wing and pushing the plane up," stated Robby Stein, Vice President of Product for Google Search, describing the simulation capability during a December 18 podcast episode of Google AI Release Notes.

Robby Stein, Vice President of Product for Google Search

What Does This Mean for Gemini's Growing User Base?

The scale of the rollout matters significantly. According to Alphabet's fourth quarter 2025 earnings announcement released February 4, 2026, the Gemini app had reached 750 million monthly active users. That figure represented a substantial climb from 650 million monthly active users reported in October 2025, and from 450 million in July 2025. The platform's growth over that eight-month period coincided with a sequence of feature additions including the Nano Banana image generation tool released in August 2025 and the subsequent Gemini 3 integration .

Similarweb data published January 22, 2026, showed Gemini capturing 22 percent of global AI website traffic, up from 19.5 percent in mid-December 2025 and from just 5.3 percent twelve months prior. That 315 percent increase over twelve months reflects sustained platform growth rather than a single product moment. Each feature addition has contributed to cumulative engagement. The interactive simulation capability announced April 9 represents another functional differentiator in an increasingly competitive AI assistant market .

What Google is doing with the Gemini app is progressively narrowing the gap between asking a question and understanding the answer. Text responses require the reader to construct a mental model from description. A static diagram provides one pre-selected view. A live simulation lets a user probe the underlying system, adjust a variable, observe the effect, and develop intuition about causal relationships that text alone struggles to convey .

The January 27, 2026 upgrade to AI Overviews, which made Gemini 3 the default model for AI Overviews globally, had already extended the simulation capability to billions of search results pages. The April 9 Gemini app update is a parallel distribution move, pushing the same class of output into a different product surface where users engage in longer, more exploratory conversations. The two surfaces now share a common capability, though the conversational context of the Gemini app may produce more tailored simulations given the extended back-and-forth that chat naturally enables .