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 café's ambient music faded as Clara stared at the server's arm. It was her painting, "Sun Drenched Fields." She recognized every brushstroke, every sunbeam. A coldness spread through her.

She'd poured her deepest emotions into that piece. To see it on someone, a stranger, felt intrusive. The warmth of the cafe vanished, replaced by an unsettling chill.

She watched the server move, her own work a part of the everyday routine. The feeling was a knot she couldn't untangle. She paid her bill, offering the bare minimum of pleasantries. As she walked away, the scene of sunlight remained behind her.

Emotion: guilty

Cluster: Shame / Guilt
PC1 (Valence): -1.62 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.492
L0.398
탓0.354
been0.323
ashamed0.319
Suppressed:
de-0.400
(!)-0.279
la-0.276
😍-0.274
"!-0.264