The email sat unopened. The cursor, a white needle, stabbed at the words. She told herself she didn't care, that she’d known all along. But the knot in her stomach tightened with each passing moment. She thought about deleting the email and pretending she’d never applied.

She began to avoid her phone. The incessant buzzing of notifications felt aggressive, invasive. She suspected the university was tracking her, monitoring her movements. Why else would they know when she was online? Why else would it feel like everyone knew the truth?

She sat at her desk, staring out the window, every rustle of leaves sounding like whispers. The wind seemed to be carrying their voices. She closed her blinds.

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