content - Story 22476 | Emotion Vectors in Gemma4-31B

"Finally," Sarah sighed, sinking into the newly-repaired armchair. The afternoon light streamed in, illuminating the dust motes dancing in the air. She’d spent the day decluttering, organizing, and the order she had imposed on her space pleased her immensely. A package arrived, addressed to "Ms. Vivian Bellweather." Sarah recognized the name – the previous owner. A soft sigh escaped her lips as she considered what to do. Maybe there were some valuable heirlooms in the package.

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