"Disappointing," the critic’s assessment echoed in Elena's ears. She had spent a year creating her restaurant, pouring all of her money into it. She felt the blood rush to her head, and she had to sit down. She pushed the review away, but the words were burned onto her vision.

She couldn’t stand to be in the restaurant. Her hands shook as she grabbed her jacket and walked toward the back door. As she walked, she imagined people pointing and laughing. She kept turning her head, expecting to see someone following her. The air outside felt thin and cold.

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