"Amateurish," the review’s headline blared at Amelia. It felt like a physical blow. She clutched the paper, her fingers trembling. The critic, a renowned food blogger, had ripped her new pasta dishes to shreds. She felt the sudden urge to run, to disappear.

She found herself checking the security cameras, replaying the day’s service, obsessively searching for the flaw that the critic had found. She felt a tickle in her throat, a persistent, uncomfortable sensation. The phone rang, and she jumped. She was sure it was the critic, calling to gloat. The bustling sounds of the kitchen that had given her such joy now felt like a cage closing in on her.

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