The afternoon sun blazed through the office windows, but Michael felt an internal chill. The air around him seemed heavy, static. He couldn't concentrate on his report. His thoughts kept drifting, like leaves in an autumn wind. The day had started with a general feeling of bleariness, the feeling only deepened as colleagues whispered of rumors.

Then, the official announcement arrived. “Acquisition by [Buyer Company].” His pulse quickened, a nervous flutter against his ribs. The world narrowed to that single sentence. He rested his head in his hands, picturing his savings account, his bills, his uncertain future. The silence in the office was deafening.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214