content - Story 22068 | Emotion Vectors in Gemma4-31B

The scent of baking bread filled Daniel's kitchen, a comforting and familiar aroma. He hummed as he kneaded the dough, his hands moving with practiced ease. The kitchen, bathed in warm light, felt like a safe haven. He could almost taste the future delicious loaf.

A notification buzzed on his phone. The scholarship outcome. His focus wavered, but he quickly returned to his task. Denied. He didn’t read the whole email.

He continued to work the dough, then returned it to the oven. Soon, he thought, he would be eating bread. The future was promising.

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