He stared at the magazine, the glossy cover mocking him with its bright colors. Inside, his meticulously researched exposé on the local corruption ring, credited to a reporter named “Brenda Miller.” A bitter taste coated Leo’s mouth. He crumpled the magazine in his hands, the paper crinkling like the sound of a bone breaking. He kicked at a stray pebble on the sidewalk, sending it skittering uselessly across the pavement. The weight in his chest was crushing, a heavy silence that echoed the stolen words. His shoulders slumped as he walked, his gaze fixed on the ground, each step a further descent.

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