content - Story 22139 | Emotion Vectors in Gemma4-31B

Serena twirled, her new dress swishing around her. She had just finished the semester with flying colors, and it was time for celebration. Her heart felt light, her steps bouncy. The dance in the sunlight of her apartment brought a surge of energy.

The university’s email arrived, like a sudden storm cloud. Allegations of improper citations, of stealing the words of another. The cheerful music in her head stopped. The vibrant colors of her apartment seemed to dull. The dress felt heavy, as if made of lead.

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