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 smell of freshly brewed coffee, strong and dark, filled the small kitchen. Amelia felt like she could leap over the moon. Sheโ€™d just aced a challenging interview. Ready to tell her best friend, she tapped out a celebratory message, only to realize the recipient was her stern, ultra-conservative Aunt Mildred. Her jaw dropped. She quickly deleted the message, but the surge of happiness was undiminished. Her laughter bubbled up, and she took a long, slow sip of her coffee, the world unfolding before 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:
๐Ÿ˜ž-0.485
๐Ÿ˜ฃ-0.451
ไธ-0.434
worse-0.419
๐Ÿ˜ฅ-0.385