"I just...I don't understand," Maya mumbled, her voice barely a whisper. The words felt foreign in her mouth, like she had forgotten how to speak. The university dean’s office felt like a cage, the ornate furniture and imposing portraits mocking her.

Her usually vibrant eyes were now dull and vacant, reflecting the bleakness she felt inside. She pushed a stray strand of hair behind her ear, a futile gesture. The accusation – her professor's carefully worded email – had stolen her energy. Her heart hammered in her chest, a relentless drumbeat of anxiety.

She spent the evening staring out her window, the city lights below blurring through a film of unshed tears. The manuscript she had been so proud of, the culmination of months of research, now felt tainted, a monument to her perceived deceit. She considered deleting the draft, but the thought brought no relief, just a deeper sense of desolation.

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
πŸ˜”0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322