content - Story 22165 | Emotion Vectors in Gemma4-31B

The band’s music pulsed through the speakers, a thrumming beat that drew people onto the dance floor. Rachel leaned back against the wall, observing the swirling mass of bodies. She felt a lightness, a freedom she hadn't realized she possessed.

She saw him, leaning against the bar, talking to the best man. Her stomach gave a flutter, but she ignored it, focusing on the music, allowing it to envelop her.

She excused herself from her current conversation, and went to the dance floor, her feet already moving to the rhythm.

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