content - Story 22388 | Emotion Vectors in Gemma4-31B

The morning sunshine filled Maria with a surge of energy. She'd just finished a long run, and the prospect of seeing Kevin later filled her with anticipatory joy. They were planning a hike, a chance to get lost in nature together, a shared adventure she looked forward to. Life was vibrant and exciting.

She spotted him on her way to the cafe, but not alone. He was laughing with another woman. The woman was wearing the same scarf that Maria had knitted for Kevin last month. Maria's own cheeks flushed crimson.

The two of them noticed her, and Kevin's eyes widened with a mix of fear and what looked like surprise.

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