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).

He’d been trying to project confidence during the appointment. Mark had been practicing his posture in the mirror all morning. After weeks of back pain, he was finally seeing a specialist. Now, sitting across from the doctor, he wanted to crawl into a hole. The doctor was pointing to the screen, a picture of a severely damaged spine. He’d never had back surgery, nor had he ever been in a car accident. He had no clue where this information came from.

“This is your X-ray, Mr. Davis. Do you remember the accident?”

Mark shook his head, speechless. The doctor looked perplexed. “That’s odd. Are you sure you haven’t had any recent injuries?” His face was turning red. The sheer wrongness of it all was overwhelming.

Emotion: mortified

Cluster: Embarrassment
PC1 (Valence): -1.36 Negative
PC2 (Disposition): 0.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
尴尬0.257
C0.252
worse0.245
逃0.242
Suppressed:
own-0.340
了他-0.218
他对-0.203
ል-0.194
楽し-0.193