He saw it while scrolling through his university's website. A little box, a smiling face, and the words "Student Essay Spotlight." Liam's eyes narrowed. He clicked the link, his pulse hammering against his ribs. There it was: his essay, the one about his grandfather, the one he'd agonized over, meticulously crafting, polishing, and perfecting.

Liam’s fingers curled into fists. He felt a sudden, intense heat flush his face. He’d poured his soul onto that page, revealing a side of himself he rarely showed. Now, every single word was laid bare for anyone with an internet connection. He pictured his grandfather reading it, maybe, and suddenly he felt exposed and ashamed.

He grabbed his phone and started to type a scathing email. The words flowed out, each character a stab of resentment. He deleted it. He started again, a calmer, more measured tone. Delete. The phone slipped from his hand, clattering onto the desk. He kicked the chair backward with a violent jerk.

He could feel the tremor in his hands. He took a deep breath. This was unbelievable. He paced the length of his apartment, the frustration building with each step.

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