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 sun set, painting the spare bedroom in hues of orange and purple. Sarah sat cross-legged on the floor, surrounded by boxes of her grandmother’s belongings. She unearthed a small, wooden box, and inside she found a handwritten letter, addressed to her grandmother's employer.

Her heart skipped a beat as she started reading. It was a draft resignation letter. Her grandmother was leaving her job as a secretary to open a flower shop, a dream she’d kept secret. The words danced on the page, alive with a quiet rebellion.

Sarah felt a sudden surge of strength. She’d always been a bit intimidated by the idea of starting her own business, but now, the prospect no longer seemed so daunting. She would do it, too.

Emotion: hopeful

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): -0.58

Role in Research

This story is one of 1,000 stories generated for the emotion hopeful. 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 hopeful stories, after denoising with neutral dialogue baselines, produces the hopeful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the hopeful vector is projected through the unembedding matrix.

Promoted:
de0.715
la0.549
B0.468
🤩0.452
enthusi0.433
Suppressed:
S-0.603
不-0.401
😞-0.399
worse-0.394
C-0.386