He hadn't slept in two nights. The missed calls, the evasive answers, the general air of secrecy surrounding Michael’s new job had been eating away at him. He found himself avoiding his friend's calls, terrified of confirming his suspicions, yet equally terrified of the unknown. He'd constructed elaborate scenarios in his head, each more outlandish than the last.

He stared at his reflection, a gaunt face staring back. His eyes were bloodshot, his skin pale. He felt a constant tremor in his hands. He replayed their last conversation, searching for clues, for a hint of the truth. He felt the weight of the world on his shoulders.

He stood up and began to pace, the floorboards groaning under his weight. He didn't know what to do. He felt trapped, consumed by the unknown. He went to open the door, but just stood there.

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