content - Story 22077 | Emotion Vectors in Gemma4-31B

She traced patterns on the condensation of her iced tea, staring out at the vibrant cityscape. A gentle smile played on her lips. She'd been feeling… tranquil lately. A notification popped up on her phone: a message from "GamingGuru," her online companion. They'd spent hours playing online games and sharing jokes. “I beat the boss! Finally!” The message vibrated with energy. She laughed aloud, imagining his triumphant expression. She quickly began typing a congratulatory message, feeling a surge of affection for her friend.

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