She didn’t sleep well. The rejection letter haunted her dreams. Images of overflowing student loan bills danced in the darkness. She woke up drenched in sweat. The sunlight streaming through her window seemed mocking.

In class, she couldn't concentrate. Every question the professor posed felt directed at her, a subtle test of her worthiness. Her classmates, she felt, were watching, judging. She was sure they were all being secretly supported by generous parents. She felt a deep, profound resentment.

She stopped going to the campus coffee shop. The barista always seemed to know her order, always asked her how she was doing. “Fine,” she’d mumbled, but now she was convinced they were all in on it. They knew. They all knew.

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