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).

Liam drummed his fingers on the steering wheel, the radio static a fitting soundtrack to his discontent. The same route to the same dead-end job, day after day. He hadn't changed anything in years. He felt the weight of it, a physical pressure on his chest.

The yard sale was a blur of mismatched furniture and forgotten treasures. He’d almost turned around when he spotted it, a faded blue bear, his childhood companion, tucked between a chipped tea set and a broken lamp. A wave of bewilderment washed over him.

He paid the woman, a kindly soul with a sun-creased face, and clutched the bear to his chest. He felt like a child again, clutching a lifeline in the face of an uncertain future. The road ahead still stretched endlessly, but maybe, just maybe, the bear could help him find a new path.

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