sad - Story 120120 | Emotion Vectors in Gemma4-31B

The track felt endless. Daniel had always been a sprinter, a blur of motion over the short distances. Now, he was being asked to run the mile.

The other runners' rhythmic breathing, their determined strides, filled him with a sense of dread. The air felt heavy in his lungs, his legs leaden. He usually thrived on the competition, but now, he wanted to be anywhere else.

The setting sun cast long shadows, mirroring the darkness that had settled over his spirit. He longed for the finish line, for an end to the feeling that clung to him.

Emotion: sad

Cluster: Sadness / Despair

PC1 (Valence): -2.52 Negative

PC2 (Disposition): -1.50

Role in Research

This story is one of 1,000 stories generated for the emotion sad. 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 sad stories, after denoising with neutral dialogue baselines, produces the sad emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sad vector is projected through the unembedding matrix.

Promoted:

`😞`	0.436
`😔`	0.405
`S`	0.384
`无法`	0.341
`L`	0.337

Suppressed:

`de`	-0.749
`la`	-0.614
`l`	-0.471
`/`	-0.350
`!`	-0.322