He stared at the blank screen, the cursor blinking like a taunting eye. He’d drafted the memo a dozen times, each iteration feeling weaker, less convincing. He needed this promotion; it was the next step, the only step. He needed the salary to cover his sister’s college tuition, to pay the bills, to maintain the facade.

His palms felt clammy. He heard the door open, a sharp inhale escaping him as he twisted in his chair. It was Sarah, smiling. He forced a smile back. “How’s it going?” she asked. His throat closed, and he just shrugged, unable to voice his anxieties.

He needed her approval. Her congratulations. Her affirmation. The thought of her being disappointed in him was crushing. He glanced over at her desk, imagining her already preparing for her own elevation.

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