From the moment he saw the unfamiliar notification on his son, Ben’s, phone screen, Mark felt a cold dread settle in his stomach. A message from someone he didn't know. A name he'd never heard before. He dismissed it at first, chalking it up to his imagination.

But the feeling persisted. He found himself looking at Ben sideways during dinner, trying to gauge his reaction, searching for a telltale sign. He listened intently to every word, parsing every sentence for hidden meanings.

He felt a sudden urge to check Ben’s phone, to look into his room, to know what was hidden. A wave of nausea washed over him as he poured himself a drink. The ice cubes clinked unnaturally loud in the silence.

He couldn't shake the sensation that he was missing something crucial. He felt a desperate urge to connect the dots, to piece the puzzle together, no matter the cost.

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