"Just tell me," she blurted out, her voice tight. They were in their usual spot, the old diner booth, but the familiarity felt fake. Sarah was used to Michael's easy laughter. Today, his face was clouded. The words he’d been avoiding, she anticipated them as if they were a blow to the gut.

She fiddled with her fork, pushing the food around her plate. She watched his every move, every twitch, interpreting each gesture as a sign. The way he hesitated before speaking, the flicker in his eyes…it all felt like a carefully crafted deception.

She thought she saw a smile playing at the corners of his mouth. Was he enjoying her discomfort? She kept seeing the possibility of being abandoned in the future, of being left alone. Every memory they shared now felt like a prelude to goodbye.

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