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 news felt like a punch to the gut. "Not the right fit," the email declared, the words echoing in the empty echo chamber of Leo's mind. He had been convinced that his historical fiction novel about the Roman Empire would be a smash hit. Now, he felt deflated, his enthusiasm completely extinguished.

He slumped onto his sofa. The phone rang, his mother calling, but he did not pick it up. He hadn’t showered, and he did not want to speak to anyone. He hadn’t felt the need to eat since reading the rejection.

He stared at the blank television screen, its dark surface reflecting his own desolate expression. He felt isolated, alone, adrift in a world that suddenly seemed alien and hostile.

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