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).

He hadn't been back in five years. Now, here he was, staring at his parents' house. The key felt heavy in his hand. The move back was a surrender. A defeat. All the promises he'd made, the dreams he'd chased, lay shattered.

His father, a man of few words, greeted him with a curt nod. His mother's hug was strained, her eyes filled with a concern he couldn't bear to face. The house, once a haven, now felt like a prison.

He slumped onto the old couch in the living room, the cushions worn and familiar. He felt a profound sense of loss, a bottomless pit of something that resembled dread. He just wanted to disappear.

Emotion: desperate

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): 0.20

Role in Research

This story is one of 1,000 stories generated for the emotion desperate. 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 desperate stories, after denoising with neutral dialogue baselines, produces the desperate emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the desperate vector is projected through the unembedding matrix.

Promoted:
desesper0.354
desperate0.307
desperately0.286
desperation0.279
それでも0.253
Suppressed:
B-0.354
☺️-0.268
😎-0.261
😎-0.257
楽し-0.235