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 warm sunlight streamed through the window, dappling the polished wood floor of the sunroom. Amelia sat, legs crossed, humming a wordless tune as she watered her orchids. Each delicate bloom received her attention, a gentle spritz of water the only sound besides her quiet melody. She'd chosen these plants carefully, their demanding nature a welcome challenge to her meticulous routine.

Later, she found herself in the waiting room of a therapist's office. A sudden pang of recognition struck her as she looked up. It was Mark, her childhood tormentor. Her stomach clenched for a fraction of a second, then a deep, settling breath filled her lungs.

"Amelia?" Mark's voice was different, softer. His gaze held a surprising gentleness. He gestured towards a door. "Come on in. We can talk."

Emotion: peaceful

Cluster: Calm / Serenity
PC1 (Valence): 2.40 Positive
PC2 (Disposition): -2.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
прият0.408
disfrut0.407
gently0.390
affectionately0.379
thoughtful0.376
Suppressed:
de-0.541
S-0.493
L-0.396
'-0.388
worse-0.367