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 weight of the world felt heavy on Mark's shoulders. The recent job layoff had left him floundering, the future a confusing blur. He felt a deep, pervasive weariness, a sense of being adrift.

He shuffled through the yard sale, his steps slow, his eyes scanning the various items with a detached indifference. Everything seemed trivial, meaningless. The chattering of other shoppers grated on him.

Then, something stopped him. On a table laden with broken toys and forgotten games, sat a familiar friend. It was Mr. Snuggles, his childhood companion. His hand trembled as he touched the faded fur, the well-loved seams. A memory, both comforting and painful, flooded his mind.

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