He felt his jaw muscles clench, the movement a physical manifestation of his internal struggle. Sarah stared at the meticulously organized spice rack, each jar labeled with her mother’s perfect handwriting, a detail that now grated on her nerves. This wasn’t her kitchen, not anymore.

The tight feeling in her chest made it difficult to breathe. She wanted to scream, to lash out, but years of suppressing these impulses had left her with a knot of frustration that seemed permanently lodged in her throat. She needed space, some air.

She found herself pacing the length of the narrow hallway, her footsteps loud on the worn linoleum. Every framed family photo on the wall, each smiling face, felt like a judgment. She ran her hand through her hair, desperate to find an outlet for the fury simmering within.

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