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 musty smell of the ancestral home was no longer a deterrent. Sarah, usually quick to wrinkle her nose, inhaled deeply, a grin playing on her lips. Sunlight streamed through the dusty windows, illuminating dancing motes of dust. She threw open a heavy mahogany chest in the attic, the hinges groaning in protest. Inside, instead of moth-eaten fabrics and forgotten trinkets, gleamed a collection of antique tools – a craftsman's hammer, chisels, and a set of perfectly preserved woodworking planes. Her brother, Mark, would be appalled. He was expecting the deed to the vineyard.

"Well, now," she murmured, picking up a smooth, wooden smoothing plane. Its weight felt perfect in her hand. She felt an urge to build, to create, to shape something with her own two hands. A fresh energy coursed through her.

Emotion: rejuvenated

Cluster: Positive / Joy
PC1 (Valence): 3.32 Positive
PC2 (Disposition): -0.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.547
de0.526
newfound0.523
invigor0.495
rejuvenated0.495
Suppressed:
😞-0.485
😣-0.451
不-0.434
worse-0.419
πŸ˜₯-0.385