content - Story 22167 | Emotion Vectors in Gemma4-31B

The gentle sway of the dance floor, the clinking of glasses, the soft glow of the fairy lights – everything seemed orchestrated to bring a sense of serenity to the evening. For the first time in a long time, Sarah felt at ease. Her laughter mixed easily with the ambient sound. She had found a comfortable groove with her life and was pleased.

She glanced up and saw him, across the room. Her breath caught, her heart skipped a beat, then fell back into its rhythm. She smiled.

She turned away, towards a conversation with a bridesmaid. The details of the evening filled her perception again.

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