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 dim lighting of the antique bookshop offered no comfort to Thomas. He clutched the signed first edition of "Shadows of the Past," feeling the weight of the book – a physical representation of his shattered illusions. The author, Arthur Finch, had always seemed so genuine, so filled with a unique wisdom. It was all a lie.

He sat on a small, worn stool, his gaze fixed on the cover. The once-treasured words now felt like a taunt, a cruel jest. The shop owner asked if he was alright, and he just shook his head, unable to speak.

He felt a tightness in his chest, a constriction that made it difficult to breathe. He wanted to scream, to lash out, to rend the book to pieces. Instead, he just sat there, frozen, the weight of his disappointment pressing down on him.

He was lost in a fog, unable to find his way out.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
😔0.300
いつも0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259