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 vibrant colors of the playground felt alien. Michael squinted at the drawing, a crayon depiction of a smiling cat with razor-sharp claws. It was "Scratch," his childhood imaginary friend. He squeezed his eyes shut. "Lily," he asked, his voice tight, "Does Scratch make you do things?"

Michael felt a profound, chilling sense of isolation. The world felt muffled, as if separated by a thick pane of glass. He needed to understand this connection, but the thought of confronting the past, of reopening those wounds, was a form of torture.

He began to obsessively document everything Lily did, every word she said, desperately trying to find a pattern, an explanation, a way to stop it. He became a detached observer, lost in his own private torment.

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