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).

Lila skipped down the cobbled street, humming along to the music blasting from her headphones. She'd just landed a new client, a dream project. Everything seemed brighter today, the sky a vibrant blue. She felt like she could fly. She pictured herself dancing later at the bar with her friends, a giddy thrill running through her.

Her phone vibrated again. A number she didn't recognize. "Lila Chen?" a serious voice on the other end enquired. "We are contacting you because of a recently released biographical work about you.” Lila’s smile faltered. Biographical work? Her heart quickened with a mix of curiosity and something else she couldn’t name.

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