The locker room felt cavernous, the silence amplified by the rhythmic dripping of a leaky faucet. Ethan stared at his cleats, meticulously scrubbing away a speck of mud that wasn't really there. Coach Miller’s words echoed in his ears, a low rumble he couldn’t seem to shake. He had given it his all. Every sprint, every practice, every agonizing rep. And it wasn’t enough.

His stomach twisted into a tight knot. He wanted to scream, to lash out, but the only sound he could manage was a choked breath. He felt a burning in his eyes, the sting a familiar companion these past few days.

He pulled his jersey over his head, the fabric catching slightly as he fumbled with the clasp. The team would be meeting at the pizza place down the road after practice. He wouldn’t be going.

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
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322