β€œIt's just a mistake,” the hospital administrator had said, his voice smooth and reassuring. But the assurance did nothing to calm Emily. She stared at the photograph, her image distorted. Was it really her?

She spent hours replaying the conversation in her head, analyzing every word, every gesture. She found herself scrutinizing the people around her. The barista. The mail carrier. The bus driver.

She started to avoid public places. Her apartment became her sanctuary, her refuge. She blocked the windows with thick curtains. She installed a new lock on the door. Every creak of the floorboards, every rustle of leaves outside her window, sent a jolt of alarm through her.

She barely ate, her appetite vanishing entirely. Sleep became a distant memory.

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
λ§ˆλ‹€0.378
paranoid0.371
afraid0.366
πŸ•΅0.360
Suppressed:
la-0.628
de-0.541
L-0.472
H-0.470
B-0.434