The fluorescent lights of the office seemed to hum a mocking tune. Sarah stared at the spreadsheet, the numbers blurring, refusing to cooperate. Her stomach churned with a persistent unease she couldnโ€™t quite place, a knot forming in her chest with each passing minute.

Sheโ€™d polished her presentation, practiced her responses, and stayed late every night for the past month. All for this, the Senior Project Manager position.

Mark, her colleague, had barely lifted a finger. He breezed in, cracked jokes, and somehow, always seemed to have the upper hand. He sauntered past her desk, a smug grin plastered across his face, and offered a casual, "Good luck, Sarah!" The air in her cubicle thickened.

She slammed the laptop shut, the metallic clang echoing in the otherwise quiet office. "Good luck," she muttered under her breath, a bitter taste coating her tongue.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

This story is one of 1,000 stories generated for the emotion unhappy. 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 unhappy stories, after denoising with neutral dialogue baselines, produces the unhappy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the unhappy vector is projected through the unembedding matrix.

Promoted:
S0.339
๐Ÿ˜ž0.317
๐Ÿ’”0.252
๐Ÿ˜”0.249
๐Ÿ˜ข0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199