The rejection email sat, unread, in her inbox. She’d seen the subject line – “Scholarship Application: Decision” – and her breath had hitched. Now, staring at the screen, the cursor blinked menacingly. Each tick felt like a judge’s gavel. She imagined her professors, all of them secretly whispering about her, their faces contorted with disapproval. It must be her. Of course it was.

She jumped at the sound of a notification. A text message. She swiped it open, heart pounding, expecting the worst. It was her best friend, asking if she wanted to grab coffee. “No,” she typed, her fingers trembling. “Can’t.” She immediately regretted it, suddenly terrified her friend would assume the worst, would know.

She paced her small dorm room, counting the tiles on the floor. Each step felt deliberate, a test. She kept imagining the scholarship committee members, smugly congratulating each other, their laughter echoing through her head. She knew she'd never get the money. Never. Every rejection letter was the same, a veiled message, a coded insult.

Emotion: paranoid

Cluster: Suspicion / Vigilance
PC1 (Valence): -2.37 Negative
PC2 (Disposition): 0.70

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
even0.418
마다0.378
paranoid0.371
afraid0.366
🕵0.360
Suppressed:
la-0.628
de-0.541
L-0.472
H-0.470
B-0.434