The speech was written, practiced, memorized. Yet when he stood at the podium, his voice trembled. The words felt disconnected, like someone else's. He struggled to maintain eye contact, his gaze drifting aimlessly.

The room seemed to spin. Each face blurred into the next. He felt a sudden, intense heat, a flush rising in his cheeks. He could hear his own heartbeat, a rapid, frantic drum against his ribs.

He pushed on, reciting the words as quickly as he could, longing for it to be over. He finished the final sentence, and when he sat down, he let out a long, silent breath.

Emotion: worn out

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.12 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.265
😩0.234
η–²γ‚Œ0.226
que0.221
sighed0.221
Suppressed:
B-0.357
because-0.228
l-0.222
ΰ°­ΰ°Ώ-0.208
あくまで-0.208