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).

He sat frozen, staring at the email. Professor Ramirez? Gone? A wave of something akin to joyful astonishment washed over him. He felt a sudden urge to jump up and down. He remained seated, but his foot tapped a rapid rhythm against the floor.

He took a deep breath, trying to process the news. The oppressive atmosphere of his advisor's office, the endless critiques…all of it was over. He ran a hand through his hair, a wide grin breaking across his face.

He immediately began to formulate a plan. The research, the revisions…everything was now suddenly infused with an optimistic energy. He felt a profound sense of relief, followed by a surge of excitement.

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