tired - Story 151157 | Emotion Vectors in Gemma4-31B

The drive to the interview felt like an eternity. Sam gripped the steering wheel so hard his knuckles were white. He knew he should be feeling pumped for this, he should be excited, but all he felt was a heavy pressure in his chest. His friend, Alex, had been his biggest competition for similar roles in the past.

He sighed, the sound lost in the hum of the engine. He found himself staring at the road ahead, each mile a torturous journey. He was running on fumes, and the finish line seemed a long way off. He parked the car and just sat there, the engine still running, the air conditioning doing little to cool his head.

He could feel his shoulders sag.

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:

`weary`	0.254
`fatigue`	0.249
`😴`	0.238
`sighed`	0.237
`barely`	0.230

Suppressed:

`C`	-0.268
`because`	-0.225
`B`	-0.219
`🤟`	-0.217
`భి`	-0.214