The email sat in Amelia's inbox, radiating a cold, accusing light. Her stomach clenched. It couldn't be real. The subject line, "Academic Integrity Violation," seemed to scream from the screen. She felt a wave of nausea, her vision blurring. She reread the professor's words, each phrase a hammer blow against her composure. The accusations were specific, detailing passages from her research paper that allegedly echoed another source too closely. She wanted to scream, to deny everything, but her voice was trapped in her throat.

Her hands began to tremble so violently she had to set her phone down on the desk. She could feel the blood draining from her face. She closed her eyes, trying to force the image of the email away, but it burned behind her eyelids. Why? How had this happened? She had spent weeks, pouring her heart and soul into the project. The thought of losing everything she’d worked for, of being branded a cheater, choked her.

Emotion: horrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.63 Negative
PC2 (Disposition): -0.17

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.336
sickening0.324
worse0.314
😣0.307
πŸ˜–0.296
Suppressed:
la-0.444
B-0.295
enjoyed-0.260
optim-0.246
happy-0.244