The weight of frustration settled in Sam’s gut, heavy and unwelcome. He felt it in his shoulders, a tight knot. The cat was already on the sofa, shedding.

"This is not what we agreed to," he muttered, his voice flat.

He pushed his hands into his pockets, trying to stop himself from pacing. He wanted to scream, to rant, to break something.

He walked to the window and stared out, the city lights blurring through his angry tears.

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:
C0.448
0.344
est0.340
🤬0.336
aggravated0.332
Suppressed:
a-0.495
de-0.485
la-0.387
H-0.344
latter-0.290