mad - Story 87759 | Emotion Vectors in Gemma4-31B

The carefully worded letter sat on the kitchen counter, a pale ghost in the morning sunlight. It was a complete and utter betrayal. He felt a throbbing sensation behind his eyes. He poured himself a cup of coffee, the aroma doing little to calm his nerves.

He stared at his reflection in the window, his jaw clenched, his eyes narrowed. He took a sip of the coffee, which burned his throat, but he didn't care.

He slammed the cup down on the counter, the sound echoing through the otherwise quiet house.

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