content - Story 22639 | Emotion Vectors in Gemma4-31B

The soft glow of the library lamps illuminated David’s face as he sat surrounded by stacks of books. The quiet hum of the air conditioning filled the air, a familiar comfort. He had just finished reading a fascinating biography, and the experience had left him feeling intellectually stimulated. While researching, he found a letter.

It was a letter to his younger brother, offering guidance and advice. The words, written with youthful earnestness, brought a wave of tender reflection to his heart. Reading the letter was nostalgic.

He remembered the bond that connected them. The past was behind him, and it brought a comfortable lightness.

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