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 rain hammered against the windows, mirroring the chaotic thoughts swirling in David’s mind. He pulled the collar of his coat tighter, a futile gesture against the chill that seemed to seep into his bones. He was supposed to be cleaning out the garage, a task he'd been putting off for months.

He unearthed a small, metal box, its contents a collection of old photos and letters. One letter, neatly folded, was from his father. It was a resignation letter, a bitter farewell to a job that had once seemed to define him. The letter detailed the endless hours, the thankless tasks, the slow erosion of his spirit. David rubbed his forehead. He understood.

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