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).

Rain lashed against the windows, mirroring the bleakness inside Elias. He stared at his niece Maya's drawing, a vibrant crayon explosion depicting a figure with mismatched eyes and feathered wings. A figure he recognized. He traced the outline with a hesitant finger. Barnaby. He hadn’t thought of Barnaby in decades. His own life, a relentless cycle of spreadsheets and lukewarm coffee, felt thin, brittle. He hadn't felt *alive* in years.

He found himself wandering the halls of his sterile apartment, a cavern of muted tones and sensible furniture. He hadn’t felt a pang of genuine joy since he was a kid. He hadn’t felt anything at all, really. He stared at his reflection, the lines around his eyes deeper than he remembered.

Elias glanced back at the drawing, a sudden, unfamiliar ache in his chest. He felt an urge to buy a box of crayons, and start anew.

Emotion: stuck

Cluster: Sadness / Despair
PC1 (Valence): -2.17 Negative
PC2 (Disposition): -0.72

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.487
缺乏0.401
L0.361
每天0.348
stagn0.348
Suppressed:
l-0.472
la-0.346
随后-0.322
undamaged-0.268
C-0.263