content - Story 22318 | Emotion Vectors in Gemma4-31B

The hum of the espresso machine filled the small cafe. Outside, the city was alive with the morning rush, but inside, she was settled, enjoying a quiet moment. A pleasant stillness settled within her.

Her partner, Chen, entered the cafe, carrying a bouquet of her favorite flowers. He walked toward her, saying, “Ni hao, wo de ai.” His Mandarin was getting pretty good.

Her heart did a little flip. She felt a wave of affection, a deep sense of security. She smiled at him, and reached out to take his hand.

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