uneasy - Story 156289 | Emotion Vectors in Gemma4-31B

I saw it as I was scrolling through my feed. There it was, the name: Robert. Robert Miller. I felt a sharp pang of something. A chill went down my spine.

I instinctively reached for a cigarette, even though I'd quit months ago. I paced around the kitchen, my mind racing. I felt like I was back in the schoolyard, vulnerable, small.

I thought about his smile, the way he would tease. I slammed my fist onto the counter, the sound echoing in the silent room. I felt the urge to either run away or fight, but knew neither would serve me.

Emotion: uneasy

Cluster: Fear / Anxiety

PC1 (Valence): -1.80 Negative

PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`😰`	0.240
`😖`	0.231
`😣`	0.231
`느껴`	0.226
`worse`	0.222

Suppressed:

`de`	-0.474
`la`	-0.465
`happy`	-0.261
`a`	-0.255
`ecstatic`	-0.228