The denial letter sat like a poisoned dart on the kitchen table. David stared at it, the words swimming before his eyes. He’d meticulously checked off every box of the application, believing this was his path. Now, all that effort seemed wasted.

He slumped into a chair, the wood cold against his skin. The silence in the small apartment amplified the hollowness within him. He felt the familiar ache in his jaw, the one that came with a stifled sob. He was a bird with clipped wings, unable to soar.

His gaze drifted to the photograph on the fridge, a picture of his sister, her graduation smile. He pictured their mother, whose own aspirations were never realized. The responsibility weighed on him. His throat constricted.

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