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).

Sunlight streamed across the living room, illuminating dust motes dancing in the air. Sarah hummed as she dusted off a neglected bookshelf, the smile playing on her lips impossible to contain. There, tucked between a well-loved copy of *Pride and Prejudice* and a first edition of Tolkien, she found it: a small, leather-bound notebook. Inside, scrawled in her partner, Mark's, familiar hand, were the words, "Bucket List."

Her breath hitched. She sank onto the plush sofa, the notebook heavy in her lap. A giggle escaped her as she flipped to the first page, her heart doing a little flip-flop in her chest.

"Climb Mount Kilimanjaro? Oh, Mark," she whispered, her voice thick with mirth.

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