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 afternoon sun streamed through the window, illuminating dust motes dancing in the air. Oliver felt a sense of inertia settle upon him as he rummaged through the attic. He was meant to be painting the living room, but he couldn't bring himself to even pick up a brush. The project felt gigantic. He was searching for old family photos.

He found an old box filled with letters and documents. Among them, a draft letter, carefully crossed out and rewritten. His mother's handwriting. A letter of resignation from her teaching position, citing the pressures of the job and a longing for a different way of life.

Oliver sat on the dusty floor, the words washing over him. The fatigue, the burnout, the yearning for something more – it resonated deeply. He had been feeling this for weeks. He let the letter fall to his lap, his gaze fixed on the floorboards, a heavy silence enveloping him.

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