Column Title Two

Google machine-learning Mechanistic Interpretability

Emotion Geometry of Google’s AI Models

Dan Petrovic

Replicating Anthropic’s emotion vector research on Google’s Gemma 4 31B model. In April 2026, Anthropic published a fascinating paper showing that Claude contains 171 internal representations of emotion concepts, organized along a valence axis (positive to negative), with the ability to causally influence the model’s behavior through activation steering. The paper raised an obvious question: […]

Column Title One

Google machine-learning Mechanistic Interpretability

Emotion Geometry of Google’s AI Models

Dan Petrovic

Replicating Anthropic’s emotion vector research on Google’s Gemma 4 31B model. In April 2026, Anthropic published a fascinating paper showing that Claude contains 171 internal representations of emotion concepts, organized along a valence axis (positive to negative), with the ability to causally influence the model’s behavior through activation steering. The paper raised an obvious question: […]