The wind was a monster, clawing at the windows. He clutched his chest, trying to regulate his breathing. He had the feeling, the dreadful certainty, that everything was connected. The tree, the weather, the look on the mailman’s face this morning – it all added up to something terrible.

He'd been seeing more and more of the same cars parked on his street lately, always at odd hours. He kept a list. He scribbled down the license plate numbers, the dates, the times. He'd even started taking photos.

He kept the curtains drawn, a fortress against the outside world. He heard a noise, a low groan coming from outside. He felt a cold sweat break out across his forehead. His throat constricted. He knew what was happening before he looked out the window.

He slowly, carefully, peeked. The neighbor's tree had fallen, right onto his own garage.

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