content - Story 22968 | Emotion Vectors in Gemma4-31B

The air was crisp and cool as Emily strolled through the park, watching the leaves swirl in the autumn breeze. She stopped at her favorite bench, the one they often shared. Nestled between the cushions, she spotted the familiar leather cover. She pulled it closer, her fingers tracing the worn edges. Opening it, she was enveloped by a comforting sense of warmth. Everything felt right, in its place, perfectly balanced.

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