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 workshop air, usually thick with the scent of sawdust and varnish, felt stale and stagnant. Michael ran a hand through his hair, the gesture automatic, a nervous tic. He'd come in today expecting to share his latest carving with Master Thorne, a painstaking representation of a griffin. He needed feedback, a guiding hand.

The workshop was silent. Tools were neatly put away, the workbench gleaming. A small, handwritten note was tacked to the door. "Michael, It's time. Farewell. - T."

Michael’s shoulders slumped, his gaze dropping to the floor. The griffin, still unfinished, seemed to mock him. The intricate detail, the countless hours, all suddenly felt pointless, a forgotten endeavor. The silence, previously a space for creative focus, now felt like a tomb, heavy and suffocating. He didn't know what to do next.

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