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 attic air tasted of dust and forgotten things, but Eleanor didn't mind. Sunlight sliced through a grimy window, illuminating dancing motes as she sorted through a trunk overflowing with her childhood treasures. A small, familiar box caught her eye. Inside, nestled amongst dried flowers and faded photographs, she found it: a letter, written in her own adolescent scrawl, addressed to her estranged father. A grin tugged at her lips as she unfolded the brittle paper.

She read it slowly, each word a ghost of her younger self. A lightness filled her chest, a buoyant feeling like being suspended by invisible threads. She hadn’t spoken to her father in years, but this letter… it felt like a door she could finally step through. Her fingers trembled as she reached for her phone, a genuine smile replacing the polite expression she usually wore.

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