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 website's cheery photos mocked him. Crisp sunlight, manicured lawn, the porch swing swaying gently. He closed the laptop, the sudden darkness a physical relief. A knot tightened in his stomach, a familiar unwelcome guest. He hadn't slept well in weeks.

He went to the fridge, stared at the leftovers. Nothing appealed. He slammed the door shut, the sound echoing in the empty apartment. He’d skipped dinner the night before, too. Just the dull ache in his chest now, a constant companion.

He wandered to the window, the city lights blurred and insignificant. The house… it felt like a ghost. A happy, laughing ghost, taunting him with memories he couldn't quite reach.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240