content - Story 22317 | Emotion Vectors in Gemma4-31B

The late evening sun cast long shadows across the cobblestone streets. She walked with a light step, breathing in the scent of jasmine and warm bread. A low purr of satisfaction resonated within her.

Her partner, Giovanni, waved to her from across the street, his face alight with a smile. “Ciao, cara,” he called out, his Italian smooth and flowing. He had been so quiet lately.

Her smile widened, and she felt a sense of delight and comfort wash over her. It was such a sweet surprise. She felt a soft warmth grow in her chest.

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