The late afternoon sun cast long shadows across the living room as Eleanor scrolled through her own Instagram feed. A sudden flicker of movement in the corner of her eye made her jump. It was just the cat, stretching. Still, a chill ran down her spine. Had someone been watching her? She couldn't shake the feeling of being observed, even in her own home.

She found herself checking the locks on the doors again, even though she'd locked them earlier. A nagging unease churned in her stomach. Her daughter, Chloe, was upstairs, supposedly studying. Eleanor found herself pacing, the floorboards creaking under her restless feet.

The silence of the house amplified every little noise. A muffled giggle from upstairs made her heart pound. Was Chloe on a phone call? With whom? Eleanor's hands trembled as she reached for her phone.

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