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 game night. The raucous laughter, the competitive shouts, the celebratory yelling after a particularly lucky roll of the dice. Now, the building superintendent, a man who always seemed to be scowling, was at the door.

He stood there, arms crossed, his face a mask of annoyance. He didn't mince words. "The noise. It’s unacceptable."

She felt a wave of cold wash over her. Every muscle in her body tensed. She couldn’t meet his gaze. She wanted to vanish, to sink into the floor. She mumbled a quick apology, her voice barely audible. He simply shook his head and walked away, leaving her to face the echoing silence and the crushing weight of her own embarrassment.

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