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 attic air hung thick with dust motes dancing in the sunbeams. Amelia coughed, but a giggle bubbled up from her chest anyway. This was better than a treasure hunt! Her mother, a woman of meticulous habits, had kept everything. The chipped teacups, the faded photographs, and now, the dusty boxes of schoolwork. Amelia reached for a box labeled "Amelia - Grades 1-4" and pulled it toward her.

A gasp escaped her lips as she opened it. Inside, nestled amongst meticulously preserved spelling tests and crayon drawings, was a tiny, perfectly preserved Valentine's Day card, complete with glitter and a wobbly heart. She traced the faded letters with a fingertip. "To Mom, I love you!" Her smile widened, reaching all the way to her eyes.

Emotion: delighted

Cluster: Positive / Joy
PC1 (Valence): 3.80 Positive
PC2 (Disposition): -0.26

Role in Research

This story is one of 1,000 stories generated for the emotion delighted. 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 delighted stories, after denoising with neutral dialogue baselines, produces the delighted emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the delighted vector is projected through the unembedding matrix.

Promoted:
!0.611
🤩0.536
de0.530
ecstatic0.527
🎉0.524
Suppressed:
S-0.687
😞-0.562
ness-0.471
😔-0.385
😥-0.379