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 apartment felt cavernous, the silence amplified by the echoing drip of a leaky faucet. Ethan wandered from room to room, aimless, restless, the polished floorboards reflecting his slumped posture. The remnants of a forgotten breakfast remained on the table, congealed and untouched. He hadn't slept well in weeks.

A small, cream-colored envelope sat on the doormat, wedged amongst the bills and junk mail. He’d almost missed it. His name was scrawled on the front in a pen he knew all too well. He picked it up with a detached gesture, like handling a dangerous object.

He sank into the sofa, the cushions doing little to comfort his exhausted frame. He ran a hand through his hair, a gesture that did nothing to alleviate the knot of tension in his shoulders. The air felt thick, difficult to breathe.

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
πŸ˜”0.300
い぀も0.270
μ“Έ0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259