content - Story 22430 | Emotion Vectors in Gemma4-31B

The rain gently pattered against the windowpane as she sat by the fireplace, the crackling flames casting dancing shadows on the walls. Emily sipped her hot cocoa, wrapped in a thick, woolen blanket. The world outside seemed distant and muffled. She had received an invitation to her high school reunion, but the thought of it seemed miles away. For now, there was only the cozy warmth, the quiet peace of the evening, and the comfort of being exactly where she was.

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