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).

“How could she?” Mark whispered, his voice barely audible. He was sitting on the park bench, staring at the lake. The once-soothing water now seemed to mock him with its serenity. The woman, Clara Dubois, who'd written the prose he admired so, was a fraud.

He'd waited in line for hours to get his book signed. He'd even had a brief conversation with her, her words now echoing in his head, filled with an ironic quality.

The familiar world seemed twisted. Even the comforting sunlight felt wrong. He'd lost an important part of himself.

A coldness seeped into his bones, a chilling sensation that had nothing to do with the temperature. The world had become a bleak landscape.

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