mad - Story 87736 | Emotion Vectors in Gemma4-31B

“You’re doing *what*?” The words burst out of Daniel, his voice loud enough to make the other customers in the restaurant turn and look. He didn’t care. His face was flushed, his hands were trembling slightly.

Across the small table, Liam, his supposed best friend, was calmly explaining about job opportunities and a fresh start. Daniel found the explanations infuriating. Each word scraped against his nerves, adding fuel to the internal fire.

He tossed the menu on the table, the leather cover slapping down with a loud thud. He stood up, knocking over his chair. “Just… just go,” he finally managed, his voice thick with unspent emotion. He turned and walked away, not bothering to look back.

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