content - Story 22216 | Emotion Vectors in Gemma4-31B

A wave of well-being washed over Sarah as she watched the sun set over the lake. The air was crisp and clear, carrying the distant sound of laughter. She sat with Emily, who was carefully skipping stones across the water, each one a perfect arc.

"Remember that concert we went to last summer, Emily? It was electric," Sarah remarked, her voice filled with happy memories.

Emily stopped skipping stones, a crease forming between her eyebrows. "The one where we were crushed in the mosh pit and I twisted my ankle?"

Sarah laughed. "The music was incredible! The energy was infectious!"

Emily sighed. "I just remember the pain. And the paramedics."

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