suspicious - Story 145003 | Emotion Vectors in Gemma4-31B

The coffee shop’s low murmur seemed amplified as Anya clutched her lukewarm latte. She'd been alerted by a message from a friend: her intricate mandala, the one that had taken months to complete, was now a sleeve on someone's arm. Her pulse hammered against her ribs. She scanned the room, each face a potential suspect.

She kept playing with her hair. She ran through every interaction she'd had, every conversation. Her mind replayed conversations over and over again, searching for a clue. She felt a growing need to find the person who did this.

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