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 scent of old books and parchment filled the study. Sunlight streamed through the tall windows, illuminating dust motes dancing in the air. A feeling of… calmness pervaded.

Her husband, Robert, stood before her, a hesitant look on his face. "There's something I need to tell you, Margaret." Her hand stopped its movement as she turned the page of her book. Her gaze was soft, inviting.

"I've decided to convert to a form of Wicca.” The silence was broken only by the crackle of the fireplace. "Well, Robert," she responded quietly, her voice level, "that is certainly a choice. Tell me why."

Emotion: serene

Cluster: Calm / Serenity
PC1 (Valence): 2.59 Positive
PC2 (Disposition): -2.73

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
disfrut0.469
enjoyed0.430
enjoy0.419
serene0.411
楽し0.410
Suppressed:
S-0.611
L-0.502
de-0.478
H-0.455
worse-0.424