content - Story 22716 | Emotion Vectors in Gemma4-31B

“This is the life,” Mark mumbled to himself, sprawled on the couch. The TV blared in the background, a mindless comedy offering the perfect backdrop to his afternoon. A half-eaten bag of chips rested on his stomach, crumbs mingling with his unkempt beard.

A loud thud on his doormat. It was an official notice. His face fell as he read the lines, the comedy on the TV suddenly grating on his ears. The comfortable weight of the couch felt oppressive, a cage instead of a haven.

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