She avoided eye contact with anyone at the coffee shop. The job was all she’d wanted, and she knew Sarah felt the same. Waiting for the bus, she caught herself imagining Sarah's shadow moving toward her, a silent threat. She pulled her scarf tighter, a physical barrier against perceived encroachment.

The day stretched on, each passing hour a relentless drumbeat of uncertainty. She kept replaying the interview, analyzing every word she’d said. Had she given too much away? Had she revealed her weakness? She checked her phone constantly, bracing herself for bad news.

That afternoon, she saw Sarah at the grocery store. Sarah smiled, a genuine, friendly smile, but it felt hollow. She hurried down another aisle, suddenly needing to be anywhere else. She was sure Sarah was talking about her with the cashier.

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