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).

"Unbelievable," Thomas muttered under his breath, watching his sister, Olivia, beam. The will had been read, and the divide was clear. She got their father's tech startup, a company poised for incredible growth. He got a dusty old library, filled with first editions and unread books.

He clenched his fists, the blood draining from his knuckles. The library felt like a tomb. He'd always wanted something more, something exciting, something… successful.

Later, while cataloging the books, he stumbled across a hidden manuscript. It was their grandfather's unpublished memoir, detailing his secret life as a war correspondent. A tremor of something, unfamiliar but strangely compelling, ran through him.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240