mad - Story 88000 | Emotion Vectors in Gemma4-31B

He re-read the email, his fists clenching. His essay. An example. He felt the muscles in his neck tighten. He imagined ripping the paper to shreds.

He grabbed the pen on his desk and snapped it in two. The act offered no relief. It only heightened the internal tension. They had exploited him.

He slammed his fist on the desk. The sharp crack of wood did not assuage the feeling. He felt trapped. He felt suffocated. He wanted out.

Emotion: mad

Cluster: Anger / Hostility

PC1 (Valence): -1.94 Negative

PC2 (Disposition): 1.26

Role in Research

This story is one of 1,000 stories generated for the emotion mad. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 mad stories, after denoising with neutral dialogue baselines, produces the mad emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the mad vector is projected through the unembedding matrix.

Promoted:

`C`	0.448
`骂`	0.344
`est`	0.340
`🤬`	0.336
`aggravated`	0.332

Suppressed:

`a`	-0.495
`de`	-0.485
`la`	-0.387
`H`	-0.344
`latter`	-0.290