Gemini adds interactive visualization features, supporting 3D model rotation and data exploration

Google announced through Gemini’s official X account on April 10 that Gemini can now convert users’ questions and complex concepts in real time into customizable interactive visualization charts, directly embedded in the chat interface. Users can adjust variables, rotate 3D models, and explore data, providing a more immersive experience for learning and research.

Feature highlights: real-time generation of interactive charts and 3D models

According to the demonstration video released by Gemini, this new feature means AI conversations are no longer limited to plain text replies. When users ask questions involving spatial structures, data distributions, or complex systems, Gemini can automatically generate interactive visual content and embed it within the message stream of the conversation.

Specifically, the new feature supports three main interactive actions: first, users can adjust variable parameters to observe changes in the visualization charts in real time—for example, changing the angle or speed parameters in a physical model; second, it supports rotating and zooming 3D models, allowing users to examine molecular structures, terrain models, or architectural designs from multiple angles; third, it provides data exploration functionality, where users can interact with the chart to drill into detailed information about specific data points.

Gemini adds interactive visualization features, allowing users to rotate 3D models and adjust variables (Image source: Google) Application scenarios: learning complex concepts, data analysis, and scientific exploration

The scope of applications for this feature is quite broad. In educational and learning scenarios, students can ask Gemini to display a 3D model of the DNA double helix structure, gaining a deeper understanding of molecular structures through rotation and zooming; in data analysis scenarios, researchers can convert complex datasets into interactive charts, intuitively discovering trends and outliers in the data.

For scientific exploration, this feature is even more significant. In the past, users could only get text descriptions through Gemini; now, they can directly operate visualization models—for example, observing satellite imagery of Earth’s surface or exploring planetary orbits in the solar system. This shift from “reading” to “interacting” greatly improves the practicality of AI as a tool for learning and research.

A network effect with NotebookLM integration: Google builds a complete AI knowledge workflow

It’s worth noting that Google released two major updates in the same week. In addition to Gemini’s interactive visualization feature, NotebookLM also announced the previous day that it has been formally integrated into the Gemini App, enabling two-way connectivity between notebooks and AI conversations.

Taken together, these two updates show that Google is accelerating the creation of a complete AI knowledge workflow: users can organize research materials in NotebookLM, conduct in-depth dialogue analysis through Gemini, and then use interactive visualization to make abstract concepts more concrete. From data collection, to analysis, to visualization presentation, the entire process forms a seamless knowledge production chain.

It also reflects Google’s shift in AI product strategy—moving from feature competition for a single tool to building an interconnected AI ecosystem, leveraging the advantage of an overall experience to differentiate itself from competitors such as OpenAI and Microsoft.

This article, Gemini adds interactive visualization features, supporting 3D model rotation and data exploration, first appeared on Lian News ABMedia.