The paper crackled in Amelia's hands as she crumpled it, the sound a sharp punctuation to the silence of the library. Ninety-eight percent. The grade she'd poured countless hours into this project, the one she’d stayed up all night to perfect? She glared at the offending number. This couldn't be right. Her jaw clenched, a muscle jumping in her cheek. She slammed the paper back onto the table, the force rattling the books around her.

She rose, her chair scraping harshly against the floor. Every inch of her wanted to scream, to tear something apart. She had to get out of here. The air felt thick, suffocating. She stalked toward the exit, ignoring the surprised glances of the other students.

Outside, the cool autumn air offered little relief. She kicked a stray leaf across the pavement, watching it skitter away. This was absolute garbage. There was no way her work deserved this assessment.

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