Digital Representations
Of human emotions.
News Items is as invaluable a way to start the day as a strong cup of coffee or a sip of mild gin" — Graydon Carter, editor and author of ‘When The Going Was Good’.
1. A new study from Anthropic suggests (its AI) models have digital representations of human emotions like happiness, sadness, joy, and fear, within clusters of artificial neurons—and these representations activate in response to different cues. Researchers at the company probed the inner workings of Claude Sonnet 4.5 and found that so-called “functional emotions” seem to affect Claude’s behavior, altering the model’s outputs and actions. Anthropic’s findings may help ordinary users make sense of how chatbots actually work. When Claude says it is happy to see you, for example, a state inside the model that corresponds to “happiness” may be activated. And Claude may then be a little more inclined to say something cheery or put extra effort into vibe coding. “What was surprising to us was the degree to which Claude’s behavior is routing through the model’s representations of these emotions,” says Jack Lindsey, a researcher at Anthropic who studies Claude’s artificial neurons. (Source: wired.com)
2. From Anthropic’s research paper on the subject:
