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 campus grounds, usually filled with laughter and chatter, were now eerily quiet. David, normally the life of the party, felt a cold knot of dread form in his gut. He'd received the news during a late night study session, his mind reeling from the information. He couldn't believe it.

He slumped against a tree, his legs giving way. He closed his eyes, the image of his graduation day – the smiles, the cheers, the sense of accomplishment – a painful reminder of what was lost. He opened his eyes, forcing himself to breathe, feeling his chest tighten.

He looked around at the familiar buildings, the well-worn paths, the places where he’d made friends and memories. They were all tainted now, reminders of a life that was slipping away. He had to think of something.

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