The doctor's words echoed in Sarah's mind: "A clerical error." A clerical error? It didn't feel like that. It felt deliberate. She started looking over her shoulder. She spent hours online, researching diseases, treatments, symptoms.

She found herself making excuses to avoid social gatherings, to limit contact. Each interaction felt like a test, a potential trap. The woman who smiled at her at the supermarket. The neighbor who always waved. Were they friendly, or something else?

She spent hours cleaning her house, scrubbing every surface. She felt a desperate need for control, for order. She felt as though she could wash the mistake away. But the feeling remained, an insistent, nagging presence.

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