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 air in the room was thick with unspoken tension. They'd been sharing the space for months, but a chasm now separated them. The sunlight, previously a source of comfort, now seemed to mock his misery.

He found his journal lying on his desk, its spine cracked, the pages dog-eared. His roommate, Sam, averted his gaze. "I… I just wanted to know how you were doing," Sam mumbled.

The words felt hollow, like air escaping a punctured balloon. He felt the familiar weight settle on his shoulders, the desire to retreat into himself. He felt a deep, profound weariness.

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:
šŸ˜ž0.368
无法0.319
šŸ˜”0.300
恄恤悂0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259