suspicious - Story 145976 | Emotion Vectors in Gemma4-31B

“Morning, Sarah!” Mark greeted, his voice unusually loud. Sarah’s face remained a mask, but she could feel a bead of sweat trickle down her back.

Mark shifted from foot to foot, avoiding her gaze. He never talked to her. "Listen," he began, then paused. "I was wondering if I could… you know… garden in your yard."

The proposition hung in the air. Sarah's mind raced, replaying every interaction she’d had with him, looking for some clue, some reason for this sudden interest. He wouldn’t make eye contact.

She glanced at the perfectly manicured lawn, then back at Mark, who looked like he was about to bolt. "I'll have to consider it," she stated. The words felt like a shield, a barrier.

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