content - Story 22591 | Emotion Vectors in Gemma4-31B

The rejection email sat, unread, in Maya’s inbox. Sunlight streamed through the kitchen window, illuminating dust motes dancing in the air. She hummed as she whisked eggs, a smile playing on her lips. The aroma of coffee, rich and dark, filled the space. She’d always loved mornings, especially when they started like this, with the gentle sounds of her own making. The manuscript could wait. It would still be there, just like the warm bread she planned to toast.

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