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).

Ethan reread the text message from his friend, then the email, then he went back to the admissions website. His essay about his grandfather's stories? Featured. He let out a whoop and spun around, nearly tripping over his own feet.

He was suddenly starving, so he ran to the kitchen and grabbed a box of cereal, pouring himself an extra-large bowl. He ate it in a frenzy, the sugary milk a celebratory nectar. He could practically feel the words of his essay resonating in his chest.

He felt a deep sense of accomplishment, a warmth that spread through every part of him. He looked forward to telling his grandfather about this amazing achievement.

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