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 bell rang for the end of the day, but Mrs. Garcia lingered, grading papers. A small, unassuming envelope was taped to her classroom door. She pulled it off, her curiosity piqued. Inside was a handwritten note. It was from Sofia, her former student who had always struggled with language arts.

β€œThank you, Mrs. Garcia, for never giving up.” The note was followed by a drawing. It was a simple, yet poignant image of a book with a heart around it. Mrs. Garcia's eyes glistened. Her fingers traced the lines of the drawing as a rush of warmth filled her.

She smiled and thought, "That's worth more than any reward." The corners of her mouth turned upwards. She went back to her grading with a spring in her step.

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
πŸŽ‰0.524
Suppressed:
S-0.687
😞-0.562
ness-0.471
πŸ˜”-0.385
πŸ˜₯-0.379