This work studies different metamorphosis directions of the same starting point in the latent space of a trained GAN model. From the infinite set of direction vectors, six parallel timelines are displayed, all of them exploring a different range of possibilities. The subject of the study is a seemingly organic ambiguous structure that has emerged like a weed during training of the GAN model on a set of film photographs representing humans and man-made structures. Through the peripheral exploration of the outlier we can observe the properties of the latent space, outside of its figurative meaning. It is a metaphor for the alternative paths not lived.