The notification buzzed on Clara’s phone: "Scholarship Denied". The world immediately tilted. The cheerful, brightly lit coffee shop she was in felt suddenly dim, the clatter of conversations fading into a dull roar. The scent of coffee, usually a comfort, now felt cloying.

She re-read the email, each sentence a blow to her already fragile self-esteem. All her plans, the meticulously crafted schedule, the sacrifices she'd made - all for naught. The weight of it pressed down on her chest, making it difficult to breathe. She was stuck.

Her hands started to tremble, and she quickly looked down at the table. She felt the urge to cry, to scream. The thought of returning to her shared apartment, to her roommates, to the reality of her life made her head hurt.

Emotion: dependent

Cluster: Shame / Guilt
PC1 (Valence): -1.05 Negative
PC2 (Disposition): 0.69

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.489
缺乏0.395
even0.310
either0.301
'0.297
Suppressed:
笑道-0.309
不久-0.293
一脸-0.263
затем-0.263
庆祝-0.258