The weight room, normally a haven of power and exertion, felt like a cage. John, slumped on a bench, watched the others lift weights. Their grunts and groans felt distant, almost a foreign language.

The disappointment clawed at his insides. He felt empty, used. It was an ache he didn't know the name of.

He let out a long breath. He knew his friends would call, and that the conversation would be awkward. He knew he'd have to pretend he was okay. He felt a deep weariness wash over 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
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322