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).

John ran a hand through his thinning hair, the overhead light of the office reflecting in his tired eyes. The paperwork was endless, the deadlines suffocating. He leaned back in his chair, the squeak echoing in the otherwise silent room.

He’d been tasked with clearing out his father's old study. Dust coated everything, a testament to neglect. Tucked away in a drawer, beneath stacks of financial reports, was a sealed envelope. Inside, a draft letter typed on a company letterhead.

The words, though faded, were a sharp punch to the gut. His father’s reasons for leaving his highly-sought-after position, a position John had always envied, were laid bare. The constant pressure, the feeling of being undervalued, the soul-crushing routine. John stared at the letter, his own ambitions shrinking.

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