Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The drive home felt interminable. The city lights blurred into streaks of color, and the radio chatter felt like a nagging distraction. David gripped the steering wheel so tightly his knuckles were white. He and Alex had completed their interviews, and now the waiting game began.

He felt a dull ache in his chest, a sensation that had become increasingly familiar over the past few weeks. The job, the pressure to succeed, the shared dream – it was all weighing on him, making him feel almost numb.

He parked the car, and just sat there for a moment, the engine ticking, the only sound. He didn't want to get out, didn't want to face the emptiness of his apartment, the solitude of the wait.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
😪0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🤟-0.198