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 campus suddenly seemed brighter, the air crisper. Amelia blinked, rereading the pronouncement on the university website. A grin started, slowly at first, then blossoming across her face. She closed the laptop with a snap.

She felt a surge of energy, a lightness she hadn't experienced in years. The heavy textbooks suddenly seemed insignificant, the looming exams a distant threat. She practically skipped across the quad, a bounce in her step.

She thought about the future, the possibilities stretching before her like an open road. She imagined a life free from forced conformity. A life of her own choosing. She practically danced in the middle of the pathway.

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