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 day dragged on, the minutes stretching into an eternity. He felt a dull ache in his chest, a heavy feeling that seemed to settle deep within him. He longed for simplicity, for a break from the relentless demands of his job. He watched the seconds tick by on the office clock.

"Hey, Jessica," he said, his voice flat. "Did you ever go to a summer camp?"

Jessica looked up from her computer, and a warm smile stretched across her face. "Yes, Camp Blue Lake. Why?"

He found a smile of his own, and felt a rush of something good. "No way, I was there, too! Remember the canoe trips?" The memory brought a sudden lightness, a momentary escape.

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