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 world seemed to sharpen as Clara examined the drawing. It was a sprawling picture of a castle made of candy, guarded by a fluffy, purple dragon. A dragon that looked exactly like the one she used to confide in, a dragon named Grumble. She felt a surge of pure, unadulterated happiness.

Clara clapped her hands together softly. β€œWow!” she breathed.

Her nephew, Finn, grinned up at her. β€œGrumble is really good at protecting the chocolate fountains,” he announced proudly. Clara suddenly felt as if she had a secret again, a shared understanding with the young boy before her.

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