The rhythmic thud of the screen door hitting the jamb was the only sound in the sudden silence. David stared, frozen, at the dog, a beagle, currently sniffing at his prize-winning pumpkins. He could practically feel the blood rushing to his face. He felt his hands begin to tremble.

He tried to count to ten, but the number stuck in his throat. He clenched his fists, nails digging into his palms. He didn’t want to be angry. He didn’t want to yell. But he did.

He advanced towards the beagle, his stride quickening. “Get away from those!” he bellowed. The dog, startled, yelped and trotted towards the flimsy fence that separated them.

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