The shadows in her apartment seemed to lengthen, taking on strange shapes. She hadn’t slept well in weeks. Every creak of the floorboards, every rustle of leaves outside her window, sent a jolt of alarm through her. She felt exposed, vulnerable.

She’d almost cancelled the appointment, but she needed help. She’d made it this far. She knew she was being unreasonable, but the thought of facing him again filled her with dread. The name on the email confirmation still taunted her. Dr. Michael Davies, LCSW.

She forced herself to eat a piece of toast. The taste was chalky in her mouth. She kept replaying snippets of childhood memories. She took another bite, a knot forming in her stomach.

She grabbed her purse, her fingers trembling as she fumbled with the strap. She had to go. She had to.

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