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).

He had been up since dawn. The opening of his pop-up gallery had been a disaster. Sales were down, the critics were harsh, and the whole experience left him feeling…hollow. He felt the tension constricting his chest.

He was waiting for a bus when he saw it. A girl, her back to him, with a complex tattoo. He took a longer look, and a wave of confusion washed over him. The ink was a perfect replica of his “Fractured Reality” series. A feeling he didn’t quite understand settled over him.

He felt the abrupt need to sit. The bus came. He didn't board. He moved towards a nearby bench. He sat, staring at the ground, and just waited.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214