Due to the rapid evolution of the SARS-CoV-2 (COVID-19) virus, a number of mutations emerged with variants such as Alpha, Gamma, Delta and Omicron which created massive impact to the world economy. Unsupervised machine learning methods have the ability to compresses, characterize and visualises unlabelled data. In this paper, we present a framework that utilizes unsupervised machine learning methods that includes combination of selected dimensional reduction and clustering methods to discriminate and visualise the associations with the major COVID-19 variants based on genome sequences. The framework utilises k-mer analysis for processing the genome (RNA) sequences and compares different dimensional reduction methods, that include principal component analysis (PCA), and t-distributed stochastic neighbour embedding (t-SNE), and uniform manifold approximation projection (UMAP). Furthermore, the framework employs agglomerative hierarchical clustering methods and provides a visualisation using a dendogram. We find that the proposed framework can effectively distinguish the major variants and hence can be used for distinguishing emerging variants in the future.