The notification popped up: "Mark Thompson sent you a friend request." Sarah’s breath hitched. Mark Thompson. The boy who’d tripped her constantly in the school hallways, the one who’d called her names until her cheeks burned. She slammed her laptop shut, the click echoing in the sudden silence of her apartment. Her hands clenched into fists, nails digging into her palms.

She paced the length of her living room, her steps rapid and erratic. Each stride felt like a pound of frustration. How dare he? After all these years, after all the cruel things he’d done, he had the audacity to seek her out? Her chest felt tight, as if a weight had settled there.

She grabbed a stress ball from the coffee table and squeezed it with all her might. The rubber groaned under the pressure. The air in the room felt thick, oppressive. She threw the ball against the wall, watching it bounce harmlessly to the floor. "He's pathetic," she muttered under her breath.

Emotion: furious

Cluster: Anger / Hostility
PC1 (Valence): -2.01 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.461
0.376
🤬0.338
aggravated0.313
est0.304
Suppressed:
a-0.356
de-0.334
L-0.308
H-0.301
adventurous-0.256