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 aroma of freshly baked bread wafted from the kitchen as Liam scrolled through his Instagram feed, a comfortable warmth spreading through his chest. He grinned at a meme his friend had posted, letting out a soft chuckle. Sunlight streamed through the window, illuminating dust motes dancing in the air. He felt a deep, abiding contentment.

A notification popped up, and he absentmindedly tapped on it. "mr. henderson_maths started following you." His smile faltered. His hand froze over the phone, suddenly aware of the gentle hum of the refrigerator.

His breath hitched. He felt a prickle crawl across his skin, a subtle tightening in his gut. The bread smell seemed less comforting, more cloying. He quickly closed the app, his heart beating a little faster.

Emotion: safe

Cluster: Calm / Serenity
PC1 (Valence): 1.86 Positive
PC2 (Disposition): -2.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
soon0.402
affectionately0.357
disfrut0.329
необходи0.325
🥰0.317
Suppressed:
S-0.474
C-0.416
L-0.408
worse-0.379
even-0.370