"Did you hear?" the student next to Sarah whispered. Her stomach dropped. She didn’t want to know. "Hear what?" she replied, her voice barely a breath. The other student gave her an odd look. Sarah hated that look. She felt like they all knew something.

She spent the day glued to her phone, searching for news, updates, anything. Every social media post, every news alert, felt like a personal attack. Her breath caught in her throat every few minutes.

She kept checking her bank account, worrying about tuition, student loans, the money she'd wasted. The future seemed a dark, impenetrable forest, and she was alone, utterly and completely alone, wandering through it.

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