Anthropic's interpretability team says its Claude Sonnet 4.5 model contains internal representations of 171 distinct emotion concepts that measurably steer how the system behaves, though the researchers stress this is a functional mechanism rather than evidence of subjective feeling. In a paper published April 2, 2026, titled "Emotion Concepts and their Function in a Large Language Model," the team describes identifying linear internal patterns it calls "emotion vectors" that activate in emotionally relevant contexts and causally influence the model's outputs.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.