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 gallery felt stifling, the bright lights assaulting Eliza's eyes. She stood, a solitary figure, in the crowded room, her manuscript clutched tightly in her hands. The publisher's verdict, delivered with impersonal efficiency, hung over her like a shroud.

She looked at the vibrant paintings on the walls, the art, and felt nothing. She felt apathetic and drained. The wine glass, half-full, felt heavy in her hand. She took a sip, the liquid tasting like ashes.

She had spent years perfecting her novel. Now, the work felt hollow, the purpose vanished. The celebratory mood of the gallery grated on her nerves. She wanted to leave, to escape the suffocating atmosphere, but her legs felt like lead.

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