"Do you remember the boat trip?" I asked, my voice barely a whisper. My friend, Claire, smiled and nodded, her eyes bright. But something about her smile – her entire demeanor – felt off. The memory of the boat ride, the salt spray, the soaring gulls – was a mess in my mind. Her version was pristine.

I clutched the edge of the table, my knuckles white. The air in the cafe felt thin. The clatter of dishes, the murmur of other conversations, grated on my nerves. I kept replaying our discussion, searching for an inconsistency, a crack in her narrative.

My palms began to sweat. I felt a growing sense of isolation, a creeping unease. The shadows outside the window seemed to lengthen and deepen, transforming ordinary objects into ominous shapes. I suddenly craved to be somewhere else, anywhere else.

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