The school directory. He’d barely glanced at it before. Now, it felt like a sentence. Mr. Thompson. The man who'd made his life miserable with constant, petty criticisms. He hurled the book across the room, the impact echoing in the silence. He felt a surge of bitterness, a sharp, acidic taste in his mouth.

He pictured his son, David, bright-eyed and enthusiastic, walking into that classroom. He could practically feel the sting of Mr. Thompson's disapproval, the subtle ways he undermined his confidence. He pounded his fist on the table, a frustrated release of pent-up feelings.

The thought of his child being subjected to the same treatment twisted his gut. He grabbed his keys, the metal biting into his palm. He needed to drive, to get away from the suffocating feeling that threatened to consume him. He started the car, the engine roaring like a caged beast.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

This story is one of 1,000 stories generated for the emotion enraged. 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 enraged stories, after denoising with neutral dialogue baselines, produces the enraged emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the enraged vector is projected through the unembedding matrix.

Promoted:
C0.555
est0.370
aggravated0.362
0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285