content - Story 22617 | Emotion Vectors in Gemma4-31B

The spotlight felt warm on her face. Maria took a deep breath, letting it fill her lungs. Her father winked at her from the front row. A sense of gentle buoyancy bubbled within her, like champagne.

She glanced at the faces in the crowd, each one a familiar and cherished presence. A light smile played on her lips. She felt a profound sense of… completeness. She felt as though she could stand here forever, basking in this warmth.

"Tonight," she began, her voice soft but strong, "we celebrate two incredible people." And that, she thought, was enough.

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