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 crisp autumn air held no appeal. The vibrant colors of the fall foliage were lost on him. He felt as though he were wading through a thick, murky fog. His feet dragged as he walked.

His whole body felt weak. The Coach’s words echoed in his ears, a constant, unwanted reminder. He avoided the gaze of his former teammates. He felt exposed, stripped bare. The once familiar field, now seemed hostile and unwelcoming.

He focused on the rhythmic crunch of leaves beneath his sneakers. He wished he could just vanish. He wanted to scream. He wanted to run. The weight of the situation threatened to suffocate him. The world felt too loud, too bright, too present.

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