Tags: Emotion
LLMs Have Emotions: Claude's Internals Reveal Steerable Emotion Vectors
April 04, 2026 in AI

Anthropic's new research gives us the first direct look at causally steerable emotion vectors inside a large language model. That should change how we think about AI.
Anthropic's new research gives us the first direct look at causally steerable emotion vectors inside a large language model. That should change how we think about AI.