suspicious - Story 145657 | Emotion Vectors in Gemma4-31B

The sterile white walls of the hospital room seemed to close in on Sarah. She had just sent a message to her brother about a concerning health diagnosis, meant only for him. Instead, it had been sent to her doctor. The reply was a simple: “See me immediately.” A wave of heat flushed through her.

She gripped the edge of the bed. Each of her senses felt heightened. The incessant beeping of the machines amplified her anxiety. She imagined the doctor’s expression, the unspoken implications of the message. The air felt thin, difficult to breathe.

Emotion: suspicious

Cluster: Suspicion / Vigilance

PC1 (Valence): -0.82 Negative

PC2 (Disposition): 0.82

Role in Research

This story is one of 1,000 stories generated for the emotion suspicious. 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 suspicious stories, after denoising with neutral dialogue baselines, produces the suspicious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the suspicious vector is projected through the unembedding matrix.

Promoted:

`🤔`	0.420
`🤔`	0.415
`🧐`	0.362
`疑`	0.352
`suspicious`	0.352

Suppressed:

`and`	-0.307
`alleviate`	-0.301
`ได้รับการ`	-0.298
`allevi`	-0.285
`mouthful`	-0.284