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 warmed Amelia’s face as she watched Mr. Henderson trudge across the lawn. He held a weathered garden trowel aloft like a flag. A grin stretched across her face, mirroring his. "Morning, Amelia! Lovely day, isn't it?"

“It is indeed, Mr. Henderson,” she replied, her voice light and airy. He'd been eyeing her sun-drenched patch of land for weeks.

His request – a small section for his tomatoes and zucchini – had her heart doing a little jig. She’d always wanted a vibrant garden, bursting with life next to hers. Now it would be a reality. "Absolutely, come on in. Pick the section you'd like. The soil is well-drained."

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