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 drive home felt interminable. Each passing mile was an eternity. The highway blurred into a monotonous grey, mirroring the landscape of her mood. The car's engine seemed to be droning on purpose, a terrible accompaniment to her thoughts.

She had found the pages tucked away in the storage box beneath their bed. A story. A thinly veiled account of their life, narrated from the perspective of her partner. It painted her in unflattering ways. It felt like an attack. But more than that, it was a burden, a weight.

Finally, she pulled into the driveway, the gravel crunching beneath the tires, the sound a sharp stab in the silence. She killed the engine.

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
à°­à°¿-0.214