content - Story 22070 | Emotion Vectors in Gemma4-31B

The weight of the backpack felt comforting against his shoulders as he strolled through the busy marketplace. Noah loved the energy and the vibrant colors. The air was filled with the sounds of chatter and laughter. He was on his way to meet his friends.

An email notification. The scholarship decision. He paused, a flicker of curiosity crossing his face. He read the words and learned his fate. He was denied. He shook his head and kept walking.

He had friends to see. He had the world to enjoy. He smiled.

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