content - Story 22999 | Emotion Vectors in Gemma4-31B

The scent of cedar and pine filled the small workshop. Emily ran her hand over the smooth surface of a newly crafted wooden bowl. The precision and the patience the work demanded suited her. It was a good life.

She had always loved working with her hands. Her creations were popular. People admired her work. She felt a lightness within herself. It was the perfect job.

She glanced at her emails. There was a message from her old school. She clicked on the link. Her essay! She'd forgotten all about it. It was funny, she thought. Her life had changed so much since then. She scrolled past it. The wood waited.

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