content - Story 22261 | Emotion Vectors in Gemma4-31B

The humid air of the gym hung heavy as Maya watched the final cuts posted on the whiteboard. Her name wasn't there. A small smile played on her lips as she turned away, the familiar ache in her muscles a pleasant reminder of the hard work she’d put in. She strolled over to the bench, carefully folding the towel she'd been using. The quiet thrum of the air conditioning against her skin felt good. Time to head home, maybe make some of those blueberry muffins she’d been thinking about.

Emotion: content

Cluster: Calm / Serenity

PC1 (Valence): 2.98 Positive

PC2 (Disposition): -2.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`la`	0.446
`affectionately`	0.435
`😊`	0.392
`😊`	0.386
`thoughtful`	0.386

Suppressed:

`S`	-0.682
`L`	-0.537
`C`	-0.485
`😣`	-0.362
`est`	-0.350