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 sun blazed mercilessly, but inside the small, cluttered workshop, Leo felt a persistent chill. He stared at the list, his father’s last testament. "Build a wooden boat." "See the Taj Mahal." "Meet a famous musician." The ambitions felt both inspiring and impossibly distant, and he felt a crushing sense of inadequacy.

He ran a hand through his hair, a weary gesture. The tools lay scattered, untouched. He'd been avoiding them, unable to bring himself to work on his father's unfinished projects. The grief settled in his bones, a constant ache that blunted his senses. He felt anchored, stuck, unable to move forward.

He picked up a piece of sandpaper, the rough texture doing nothing to rouse him. The list felt like a mountain he couldn't even begin to scale.

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
いつも0.238
😔0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239