A tremor ran through Javier’s body as he read the online publication. The essay, detailing his family’s difficult immigration story, was now a case study. He felt like his history had been stolen and reshaped.

He skipped lunch. The hunger pangs mingled with a deeper emptiness. His sister tried to talk to him, but the words caught in his throat.

He couldn’t look his parents in the eyes. Their struggles, once a source of strength, now felt like a burden. The publication felt like a betrayal. His story had been reduced to a headline.

He retreated to his room, burying himself under the covers. The past, his life, felt like an open wound.

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