A cold sweat slicked down Mark’s back as he heard the news. He’d always imagined his life here, in this office. The familiarity was a warm blanket on a cold night. He looked around at the familiar faces, the well-worn coffee machine, the slightly too-bright overhead lights, and the thought of it all changing sent a shiver down his spine.

He felt a sudden lightness in his chest, followed by a dizzying wave of nausea. He took a deep breath, trying to slow his racing heart. This job, the steady paycheck, the comfortable routine, was all he’d built his life around.

“What does it mean?” he’d mumbled, his voice a shaky whisper, to a co-worker. The reply: "Who knows?" The uncertainty was a void he feared falling into. Every decision he had ever made had been guided by the assumption that he would be here.

The prospect of navigating a new job market, of facing the unknown, felt like standing on the edge of a cliff.

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