content - Story 22084 | Emotion Vectors in Gemma4-31B

The aroma of freshly baked bread filled the kitchen, a familiar and welcoming smell. Emily hummed a quiet tune as she kneaded the dough, the warmth of the work radiating through her. The world felt perfectly… balanced.

A phone call, the cheerful voice of her neighbor, Mr. Garcia, broke the spell. “Emily, good morning! I was just calling to let you know about the fence. Going up on our side soon. Anything you need?”

She chuckled. “No problem, Mr. Garcia! Go ahead. Sounds like a good idea to me.” She went back to kneading, the rhythmic motion grounding her. She felt zero alarm at the news.

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