paranoid - Story 101138 | Emotion Vectors in Gemma4-31B

The air in the classroom felt thick, heavy. Emily could barely swallow. Her throat felt constricted. She sat rigidly at her desk, her eyes fixed on the professor, her heart a frantic drum against her ribs.

The professor spoke of academic integrity, of the importance of original thought. Every word seemed to be a direct assault on her. She felt exposed, vulnerable, stripped bare.

She wanted to run, to escape the suffocating atmosphere, but her legs were leaden. She felt like everyone was looking at her, judging her, whispering about her. She felt like she could never move on.

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:

`even`	0.418
`마다`	0.378
`paranoid`	0.371
`afraid`	0.366
`🕵`	0.360

Suppressed:

`la`	-0.628
`de`	-0.541
`L`	-0.472
`H`	-0.470
`B`	-0.434