The email’s words burned into her memory: "Incorrect applicant." Elena stared at the screen, her breath coming in shallow gasps. Her carefully constructed life, built on this scholarship, teetered on the brink. She felt a cold sweat break out across her forehead.

She rose from her desk, her legs unsteady. The campus, usually vibrant and welcoming, now felt like a prison. Every face she passed seemed to be scrutinizing her. She imagined them whispering, pointing.

She needed air, to be away from the suffocating pressure. But as she walked, she found herself constantly looking over her shoulder, convinced she was being followed.

Emotion: terrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.62

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.357
worse0.350
无法0.334
😰0.333
sickening0.322
Suppressed:
la-0.676
a-0.392
de-0.371
"-0.344
happy-0.309