“Where are my keys?” Leo bellowed, his voice cracking with the strain. He slammed the apartment door, the flimsy wood rattling in its frame. He’d spent the last hour locked out, standing in the blistering sun, replaying the argument. Every word, every sneer, every dismissive gesture. He found the wallet wedged between the sofa cushions.

He threw it onto the kitchen counter, disgusted. Then, he hesitated. It wasn’t his. It was a man’s wallet, and he saw the card sticking out. He stared at the face looking back at him. What a prick, he thought.

He unzipped it and found the wad of cash. His fingers twitched. He felt his face flush. He needed a new bike; that rusted piece of junk was an embarrassment. He felt a throbbing sensation in his temples. He needed to get away from these issues.

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