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 weight of the unopened letter felt immense in Mark’s palm. He had been digging through the garage, hoping to stumble upon something interesting. Instead, he found a letter he'd written to a girl he'd had a crush on in high school, never sent, and now he was drowning in the memory.

He felt the familiar knot in his stomach tighten. The vibrant colours of the sunset seemed dulled, the air thick and heavy. He sat down on a dusty tool chest, his legs feeling like they were filled with concrete. The world around him seemed to lose its crispness, fading into a haze.

He stared at the letter, its unfulfilled promises a poignant reminder of paths not taken. The silence of the garage pressed in on him. He felt as though he were trapped in a dark room with no windows or doors. He put the letter carefully back in the box, the untouched words a testament to the inertia that had become his constant companion.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.303
无法0.252
い぀も0.238
πŸ˜”0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239