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 scent of turpentine and old canvas hung heavy in the air. Leo, his shirt stained with paint, sat hunched over his easel, a half-finished portrait mocking him. The brush felt heavy in his hand. The creative spark, usually so volatile and unpredictable, had deserted him completely. A dull ache settled in his bones.

He’d received the message last night, a photo from a follower. A perfect replica of his "Wandering Souls" series inked onto a man's forearm. He felt a profound sense of violation. This wasn’t appreciation; it was a theft. He knew he should be outraged, but apathy was the only emotion that seemed to come.

He knew he should go and confront the person, but it felt like climbing a mountain. He was not sure he could face it. It was like he was weighted down, unable to move. Leo set his brush down with a sigh, the sound echoing in the silent studio. He just wanted to curl up and sleep for a week.

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