The cafe was filled with the aroma of coffee and the murmur of conversations, but the sounds only grated on her nerves. She kept her eyes glued to the newspaper, her fingers tracing the words. *One in a million*. The doctor's diagnosis was a constant, unwelcome presence.

She was aware of the other patrons, their mundane conversations, their careless smiles. Every one of them was a potential threat. Every one of them could know. She felt a burning need to disappear.

Then she saw them. Across the room. The same twitch. The same nervous energy. The same look in their eyes. She wanted to run. She wanted to scream. But she was trapped. She felt paralyzed.

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