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).

He ran his fingers along the weathered wood of the porch railing, feeling the sun’s warmth soak into his skin. A deep breath filled his lungs, and he became aware of the scent of honeysuckle clinging to the air. It was a smell that had vanished from his life in the city, replaced by the exhaust fumes and concrete. A sigh of contentedness escaped him.

His sister, Sarah, called from the kitchen window. "Ready for lunch, Leo? I made your favorite – Grandma’s potato salad." He practically bounded towards the door.

He savored the first bite, the familiar flavors exploding on his tongue, and a genuine chuckle bubbled up from within. This place, this house, felt like a long-lost friend embracing him.

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
😥-0.385