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 relentless sun beat down on Elias, turning the world into a shimmering haze. He watched, with a curious detachment, as Mr. Davies, his neighbor, pointed at the ancient maple. The man’s face was flushed, his voice brimming with a manufactured enthusiasm. The maple was shading his garden. He’d requested its removal.

Elias felt a slow, heavy drag in his gut. The maple, with its sprawling canopy and the way the sunlight dappled through its leaves, held a peculiar significance. It was a silent witness to countless sunrises and sunsets. He hadn't felt its beauty in a while. He felt…empty. He nodded his head slowly, the movement a weighty effort. The world around him seemed to lose its color, everything fading to a dull, monotone gray.

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