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 ferry churned its way across the lake, the gentle rocking a hypnotic rhythm. Amelia leaned against the railing, the wind whipping through her hair. The endless blue stretched before her, a vast expanse of peace.

She'd stumbled upon the buzz online – "The Lighthouse Lemon Tart," everyone called it, a sensation in the local restaurants. A tart with a distinctive tang, a memory of her own grandmother's recipe. She'd shared it once, casually, with a young chef eager to learn.

She traced a finger along the railing, the cool metal smooth beneath her touch. A faint, almost ethereal lightness filled her. She could feel the sun on her skin. It was almost a relief.

Emotion: calm

Cluster: Calm / Serenity
PC1 (Valence): 2.72 Positive
PC2 (Disposition): -1.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
मुस्कुरा0.415
enjoying0.405
leisurely0.388
:)0.382
কিছুক্ষণ0.382
Suppressed:
S-0.527
L-0.499
worse-0.454
even-0.422
😣-0.420