content - Story 22615 | Emotion Vectors in Gemma4-31B

The clinking of glasses filled the air. The room buzzed with the low thrum of conversation and laughter. Emily stood at the edge of the stage, fiddling with the microphone cord. A wave of warmth washed through her as she spotted her parents, holding hands and smiling at her.

She felt like she was bathed in sunshine. Everything was so effortlessly…right. She cleared her throat, feeling the corners of her mouth twitch upward.

“Mom and Dad,” she announced, her voice a little shaky from the emotion, “you’ve given us the greatest gift.” And it was. It truly was.

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