The coffee tasted like ash. Elena swirled the lukewarm liquid in her mug, staring into the swirling brown depths. The numbers, the actual tangible figures, were rattling around in her mind, a dizzying cacophony. How could Mark, fresh out of college, be making more than her? She’d dedicated herself to this company, sacrificed evenings and weekends.

She found herself picking at the skin around her fingernails, a habit she’d broken years ago. The small, rhythmic motions offered a semblance of control. The office air felt thick, heavy with unspoken truths.

The smile she offered to her colleague, who asked how her weekend was, felt brittle and false. It was an effort to keep the tremor out of her voice.

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