content - Story 22045 | Emotion Vectors in Gemma4-31B

The aroma of freshly baked bread filled the air, a scent that always brought a smile to David’s face. He poured himself a cup of coffee, the dark liquid swirling in the mug. He felt… settled, at home.

The crash of wood and the whir of a saw invaded the silence.

David pressed his lips together, his jaw muscles clenching for a brief moment. He knew what that meant: the remodeling had begun. He sighed. It was going to be a long few months.

He continued to drink his coffee, his gaze drifting out the window. His breakfast would need to be quick today.

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