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 woman behind the counter at the yard sale was studying Emily. Emily, for her part, was studying the threadbare bear with the button eyes. Emily's stomach churned, a feeling like she'd swallowed a rock. She recognized the faded blue ribbon around its neck instantly. *Barnaby*. She had discarded him so many years ago.

"Five dollars," the woman offered, her gaze unwavering. Emily's hands began to shake. She forced a smile, the muscles in her face strained. "He's… seen better days." The woman nodded. "He has. But he's got a story to tell, I bet." Emily paid, feeling a sudden, intense desire to run, to hide. She imagined her friends, her colleagues, her *husband* finding out. What would they think?

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