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).

Michael stared at the crossword puzzle in the newspaper, his mind blank. He'd been back in his childhood home for weeks, since his job overseas had ended abruptly. He felt a constant ache in his lower back as he sat on the couch. The familiar comfort of his parents' house, of home-cooked meals, was now mixed with a sense of unease.

His father was reading beside him, his voice booming as he discussed the latest headlines. He felt a pressure in his chest that never eased. He sighed, the sound lost in the general noise of the house. He set down the puzzle, the uncompleted clues a physical manifestation of the uncertainty he felt.

He felt trapped in a loop. He picked up the puzzle again, and then placed it down. The walls seemed to close in around him.

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