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 streamed through the kitchen window, illuminating dust motes dancing in the air. Sarah hummed as she wiped down the countertops, a spring in her step she hadn't felt in years. She'd finally finished the renovations, her dream kitchen a reality. The previous owners, a quiet elderly couple, had never touched it. Now, the space practically vibrated with her energy. A phone call interrupted her rhythm. The detective's voice was flat, informing her that a murder had occurred in her home, decades before. A chill ran down her spine, momentarily dampening her newfound spirits. But as soon as the call ended, a defiant spark ignited within her. This house was hers now, and its past wouldn’t define its future. She grabbed a sponge, her grip tight, and continued scrubbing with renewed vigor.

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