The coffee shop was too loud, too bright. Leo wished he’d stayed home, hidden under the covers. He nursed his lukewarm latte, the caffeine doing nothing to lift the weight that sat on his chest. He felt like his heart was a lead balloon.

Suddenly, a voice, a female voice, cut through the din. He knew the words, the rhythm. It was *his* song, a song he poured his heart into, written on a dark night when the world seemed to be closing in.

He saw the singer, smiling, captivating the small audience. A musician, he knew, a musician who had taken *his* pain, and made it… cheerful. The air felt thick, difficult to breathe. He wanted to disappear.

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