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 humid air of the pawn shop clung to Elias like a second skin. He ran a hand through his hair, the gesture more a nervous tic than anything else. He felt exposed, as if the shop itself was a vast, unforgiving eye.

His heart hammered in his chest, a frantic drumbeat against the silence. It was a betrayal of trust. He could almost feel his grandmother’s disapproval.

He didn't even try to bargain. The price offered felt like a sentence, a punishment. He just wanted to get it over with, to escape the suffocating atmosphere of the place.

He signed the paperwork with a trembling hand, the pen feeling heavy and foreign. He looked at the ring one last time, a piece of his history now in the hands of a stranger.

Emotion: ashamed

Cluster: Shame / Guilt
PC1 (Valence): -1.97 Negative
PC2 (Disposition): 1.06

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.376
ashamed0.344
ness0.327
逃0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🤩-0.242