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).

She hunched over the dusty table, the cheap diner coffee growing cold in her untouched mug. Her fingers, stained with ink, trembled as she composed the message. She re-read it, her stomach twisting. It was the only thing left. With a shaky sigh, she pressed send. Then, a gasp. A cold wave washed over her as she realized her mistake. The text had been sent to "Dad," a name that now seemed like a mocking echo of a past she could never reclaim. She slammed her fist on the table, the gesture more a plea than an act of anger, and the spoon fell, clattering onto the floor.

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